Paper Detail
Peter Schneider-Kamp, Jacob Nielsen, Gianluca Barmina, Kenneth Enevoldsen, Lukas Galke Poech
Current large language model development relies on massive, often non-permissible datasets, creating a high barrier for researchers committed to open-source and ethically sourced data. We introduce Mimir v1, a 1-billion-parameter language model based on the Hierarchical Reasoning Model (HRM) architecture, that is trained from scratch and delivers highly competitive performance for English and sets a new state of the art for Danish using only permissible post-training data. Trained on a mixture of 161 datasets, Mimir v1 outperforms the original HRM-Text 1B and competes with larger frontier models like Qwen 3.5 4B and Gemma 4 E2B, tested across 20 benchmarks for English, Math & Code and Danish. The model is available on the Hugging Face Hub: https://huggingface.co/danish-foundation-models/DFM-Mimir
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{schneiderkamp2026dfm,
title = {DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data},
author = {Peter Schneider-Kamp and Jacob Nielsen and Gianluca Barmina and Kenneth Enevoldsen and Lukas Galke Poech},
year = {2026},
abstract = {Current large language model development relies on massive, often non-permissible datasets, creating a high barrier for researchers committed to open-source and ethically sourced data. We introduce Mimir v1, a 1-billion-parameter language model based on the Hierarchical Reasoning Model (HRM) architecture, that is trained from scratch and delivers highly competitive performance for English and sets a new state of the art for Danish using only permissible post-training data. Trained on a mixture o},
url = {https://arxiv.org/abs/2608.13517},
keywords = {cs.CL, cs.AI},
eprint = {2608.13517},
archiveprefix = {arXiv},
}
{}